Heuristic method of automated and learning control, and building automation systems thereof
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current building automation systems lack a unified operational model for managing energy interrelationships between various building components, are limited in adapting to complex systems, and require manual intervention for commissioning and optimization, making them inefficient and difficult to scale.
Innovation Solution
A closed-loop, heuristically tuned, model-based control algorithm that simulates external factors like weather and occupancy to optimize building comfort and efficiency, allowing for adaptive model fitting and real-time monitoring, enabling automated learning and reduced human intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If model-free control loops are used to manage building systems, then implementation is simple, but the system cannot adaptively tune complex models or manage sophisticated tightly-coupled systems
Solution Approach 1:
The system performs preliminary actions by pre-defining multiple candidate control models with different control strategies and parameters before actual operation. During runtime, the system selects and switches between these pre-prepared models based on real-time system states, avoiding the need for complex real-time model derivation while maintaining adaptive capability.
Solution Approach 2:
The system changes parameters by adjusting control model parameters (such as PID parameters, forecast horizons, and control weights) based on system operating conditions. This allows the control strategy to adapt to different scenarios without changing the fundamental control structure, balancing simplicity and adaptability.
2Measurement precision
If automated commissioning requires occupancy-free training periods with artificial test regimes, then system modeling can be performed, but retro-commissioning and continuous commissioning are limited
Solution Approach 1:
The system implements periodic action by continuously and periodically updating control models using real-time building operation data. Instead of one-time offline commissioning, the system performs recurring model adjustments and validations during normal operation, enabling continuous commissioning without disrupting building occupancy or operations.
Solution Approach 2:
The system uses feedback mechanisms where real-time sensor data from building operations is continuously fed back to validate and refine control models. This closed-loop approach allows the system to learn from actual building performance and automatically adjust models, achieving both high accuracy and continuous commissioning capability.
3Ease of manufacture
If existing approaches focus on simple HVAC systems with known topologies, then commissioning is straightforward, but the system cannot scale to complex ad hoc arrangements
Solution Approach 1:
The system implements universality by developing a unified control framework that can handle diverse building systems and topologies through a common architecture. The system uses universal data collection methods and model representation techniques that work across different building types, system configurations, and control scenarios, enabling scalability from simple to complex arrangements.
Solution Approach 2:
The system applies segmentation by breaking down complex building systems into modular functional units (such as individual zones, equipment components, or system subsystems) that can be independently modeled and controlled. This modular approach allows the system to scale by composing simple modular units into complex arrangements while maintaining manageable complexity through standardized interfaces.
4Ease of manufacture
If building controls use model-free approaches, then implementation is simple, but optimization becomes difficult as system complexity increases and self-knowledge for model-driven programming is lacking
Solution Approach 1:
The system implements self-service by automatically generating, validating, and optimizing control models using building operation data without requiring external expert intervention. The system performs self-diagnosis, self-tuning, and self-optimization functions, gaining self-knowledge about building performance and automatically improving control strategies, thereby maintaining simplicity while enhancing optimization efficiency.
Data Source
AI summary
Apparatuses, systems, and methods of physical-model based building automation using in-situ regression to optimize control systems are presented. A simulation engine is configured to simulate a behavior or a controlled system using a physical model for the controlled system. A data stream comprises data from a controlled system. A training loop is configured to compare an output of a simulation engine to a data stream using a heuristic so that a physical model is regressed in a manner that the output of the simulation engine approaches the data stream.